© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 16830
    Prev
    Next
    INDEX
    Explanations

    cost and resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_34_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     JM
    0.41
     getServer
    0.37
     चॉकलेट
    0.36
    剃
    0.36
    authState
    0.36
     Joni
    0.36
     फर
    0.35
     비밀
    0.35
    轭
    0.35
     Bani
    0.35
    POSITIVE LOGITS
    resources
    0.83
    Resources
    0.78
     resources
    0.77
     recursos
    0.70
    人员
    0.69
     ressources
    0.69
    人員
    0.69
    资源
    0.68
     Ressourcen
    0.67
     Resources
    0.66
    Activations Density 0.127%

    No Known Activations